Jobs

Find AI roles by technical focus, location, and employment type.

Technical focusAll
Technical focus

Select one or more; matches any selected direction.

Back to jobs

AI Infra 工程师(上海)

Location
Shanghai
Employment type
Full-time
AI Infra

Responsibilities

工作职责: 1. 训练:在PyTorch DDP/FSDP等已有框架上跑通单机多卡到多机多卡训练,处理通信同步问题,做吞吐调优(batch size/梯度累积/学习率); 2. 推理:用TensorRT/ONNX Runtime完成模型部署,做INT8/FP16/AWQ量化、剪枝,分析延迟和吞吐瓶颈到达标; 3. CUDA:能编写功能正确的CUDA kernel,理解warp调度和shared memory bank conflict,做基础kernel性能分析; 4. 框架:在已有框架代码库中做bug修复和功能添加,能独立开发新算子和优化Pass; 5. 性能:用Nsight/PyTorch Profiler收集profile,系统分析计算/通信/IO瓶颈,量化优化收益。

Requirements

任职要求: 1. 本科及以上学历,计算机、软件工程、电子工程、通信工程等相关专业; 2. 精通C/C++、Python、Go中至少一种编程语言,具备良好的编码习惯和工程规范意识; 3. 具备扎实的计算机理论基础,深入理解数据结构、算法、操作系统、计算机网络; 4. 熟悉Linux开发环境,了解基本系统工具和Shell脚本的使用; 5. 了解分布式系统基本原理,对大规模集群的调度、容错、通信机制有一定认知; 6. 了解PyTorch、CUDA编程、NCCL、vLLM、TensorRT、DeepSpeed,或有GPU性能调优经验,加分; 7. 熟悉Kubernetes、Docker等容器化技术及其在AI场景下的应用,加分。

Who this role is for

本科及以上

Company overview

无人系统/机器人感知控制

Learn about 大疆创新

Leave with unsaved changes?

Save your drafts before leaving, or discard only the changes made since the last save.

Get help

Contact Relia for help with job applications, job posting, or reviews.

Contact Reliadylan@relia.ai
Email us

You can also copy the address and contact us from your usual email service.

Job applications
Use the application method listed on the job. Contact us if a link or email does not work, or if you need help applying.
Job posting
Contact us for help registering a company, posting a job, or preparing a job listing for review.
Reviews
Contact us with questions about recruiting eligibility, job status, or review feedback.

Please describe the issue and include the job link or company name. Include an application reference if available.

Assisted listings and submissions still require verification and review.